scholarly journals One-dimensional uncertainty analysis in two-dimensional space pattern detection task: computational and human vision

2021 ◽  
Author(s):  
João Gabriel de Oliveira Mendes da Rocha ◽  
Thais Sousa Mendes ◽  
Rafael Scherer ◽  
Cláudio Eduardo Corrêa Teixeira
Keyword(s):  
Dimensional Space ◽  
Simple Algorithm ◽  
Cross Sectional Study ◽  
Human Vision ◽  
Two Dimensional ◽  
Support Design ◽  
Cross Sectional ◽  
Target Pattern ◽  
Support Tool ◽  
Space Pattern

Background: It is important to have a critical view of the support provided by Artificial Intelligence (AI) in medical context, in order to trust this support. Design and setting: Cross-sectional study (CAAE: 39292420.2.0000.5169) to measure/compare unidimensional uncertainty of an AI and a human performing the same task. Methods: to a simple algorithm written in Python (blob detection, OpenCV) and to an ophthalmologist were given the task of detecting a two-dimensional pattern (center of the optical disc) in 1,000 digital images of normal/ abnormal fundoscopies. Algorithm performed the task 1x, human performed the task 2x, both using digital register of spatial coordinates. Machine’s unidimensional level of uncertainty was measured by the respective comparison of the x and y coordinates recorded by machine and human. Human’s unidimensional level of uncertainty was measured by comparing the coordinates recorded by human itself. Data analysis was performed using R. Results: AI failed to detect the target pattern onlyin two images. On average, man and machine showed a higher level of uncertainty in the y- coordinates, which was greater (~100 units) in machine’s performance. The level of uncertainty was higher in altered fundoscopy images. Conclusion: the measure of uncertainty of AI and humans in the same task can help understand AI limitations and therefore define its usefulness as a medical support tool.

Estimating Three-Dimensional Space from Multiple Two-Dimensional Views

1993 ◽  
Vol 2 (1) ◽  
pp. 44-53 ◽  
Author(s):  
Kristinn R. Thorisson
Keyword(s):  
Visual Search ◽  
Eye Movement ◽  
Dimensional Space ◽  
Three Dimensional ◽  
Simple Algorithm ◽  
Three Dimensions ◽  
Limiting Factor ◽  
Single Subject ◽  
Search Performance ◽  
Two Dimensional

The most common visual feedback technique in teleoperation is in the form of monoscopic video displays. As robotic autonomy increases and the human operator takes on the role of a supervisor, three-dimensional information is effectively presented by multiple, televised, two-dimensional (2-D) projections showing the same scene from different angles. To analyze how people go about using such segmented information for estimations about three-dimensional (3-D) space, 18 subjects were asked to determine the position of a stationary pointer in space; eye movements and reaction times (RTs) were recorded during a period when either two or three 2-D views were presented simultaneously, each showing the same scene from a different angle. The results revealed that subjects estimated 3-D space by using a simple algorithm of feature search. Eye movement analysis supported the conclusion that people can efficiently use multiple 2-D projections to make estimations about 3-D space without reconstructing the scene mentally in three dimensions. The major limiting factor on RT in such situations is the subjects' visual search performance, giving in this experiment a mean of 2270 msec (SD = 468; N = 18). This conclusion was supported by predictions of the Model Human Processor (Card, Moran, & Newell, 1983), which predicted a mean RT of 1820 msec given the general eye movement patterns observed. Single-subject analysis of the experimental data suggested further that in some cases people may base their judgments on a more elaborate 3-D mental model reconstructed from the available 2-D views. In such situations, RTs and visual search patterns closely resemble those found in the mental rotation paradigm (Just & Carpenter, 1976), giving RTs in the range of 5-10 sec.

scholarly journals Accuracy of telephone triage in patients suspected of transient ischaemic attack or stroke: A cross-sectional study

2020 ◽  
Author(s):  
Daphne Carmen Erkelens ◽  
Frans H. Rutten ◽  
Loes T. Wouters ◽  
L. Servaas Dolmans ◽  
Esther de Groot ◽  
...  
Keyword(s):  
Clinical Outcomes ◽  
Electronic Medical Records ◽  
Medical Records ◽  
Decision Support Tool ◽  
Cross Sectional Study ◽  
Sectional Study ◽  
Telephone Triage ◽  
Cross Sectional ◽  
Support Tool ◽  
Ischaemic Attack

Abstract Background: The Netherlands Triage Standard (NTS) is a widely used decision support tool for telephone triage at Dutch out-of-hours primary care services (OHS-PC), which, however, has never been validated against clinical outcomes. We aimed to determine the accuracy of the NTS urgency allocation for patients with neurological symptoms suggestive of a transient ischaemic attack (TIA) or stroke, with the clinical outcomes TIA, stroke, and other (neurologic) life-threatening events (LTEs) as the reference.Method: A cross-sectional study of telephone triage recordings of patients with neurological symptoms calling the OHS-PC between 2014 and 2016.The allocated NTS urgencies were derived from the electronic medical records of the OHS-PC. The clinical outcomes were retrieved from the electronic medical records of the patients’ own general practitioners. The accuracy of a high NTS urgency allocation (medical help within three hours) was calculated in terms of sensitivity, specificity, positive and negative predictive values (PPV and NPV) with the clinical outcomes TIA/stroke/other LTEs as the reference.Results: Of 1,269 patients, 635 (50.0%) received the diagnosis TIA/stroke (34.2% TIA/minor stroke, 15.8% major ischaemic or haemorrhagic stroke), and 4.8% other LTEs. For TIA/stroke/other LTEs, the sensitivity and specificity of the NTS urgency allocation were 0.72 (95%CI 0.68-0.75) and 0.48 (95%CI 0.43-0.52), and the PPV and NPV were 0.62 (95%CI 0.60-0.64) and 0.58 (95%CI 0.54-0.62).Conclusions: The NTS decision support tool used in Dutch OHS-PC performed poor to moderately regarding safety (sensitivity) and efficiency (specificity) in allocating adequate urgencies to patients with and without TIA/stroke/other LTEs.

scholarly journals Accuracy of telephone triage in suspected transient ischaemic attack or stroke: A cross-sectional study

2020 ◽  
Author(s):  
Daphne Carmen Erkelens ◽  
Frans H. Rutten ◽  
Loes T. Wouters ◽  
L. Servaas Dolmans ◽  
Esther de Groot ◽  
...  
Keyword(s):  
Clinical Outcomes ◽  
Electronic Medical Records ◽  
Medical Records ◽  
Decision Support Tool ◽  
Cross Sectional Study ◽  
Sectional Study ◽  
Telephone Triage ◽  
Cross Sectional ◽  
Support Tool ◽  
Ischaemic Attack

Abstract BackgroundThe Netherlands Triage Standard (NTS) is a widely used decision support tool for telephone triage at Dutch out-of-hours primary care services (OHS-PC), which, however, has never been validated against clinical outcomes. We aimed to determine the accuracy of the NTS urgency allocation for patients with neurological symptoms suggestive of a transient ischaemic attack (TIA) or stroke, with the clinical outcomes TIA, stroke, and other (neurologic) life-threatening events (LTEs) as the reference.MethodA cross-sectional study of telephone triage recordings of patients with neurological symptoms calling the OHS-PC between 2014 and 2016.The allocated NTS urgencies were derived from the electronic medical records of the OHS-PC. The clinical outcomes were retrieved from the electronic medical records of the patients’ own general practitioners. The accuracy of a high NTS urgency allocation (medical help within three hours) was calculated in terms of sensitivity, specificity, positive and negative predictive values (PPV and NPV) with the clinical outcomes TIA/stroke/other LTEs as the reference.ResultsOf 1,269 patients, 635 (50.0%) received the diagnosis TIA/stroke (34.2% TIA/minor stroke, 15.8% major ischaemic or haemorrhagic stroke), and 4.8% other LTEs. For TIA/stroke/other LTEs, the sensitivity and specificity of the NTS urgency allocation were 0.72 (95%CI 0.68–0.75) and 0.48 (95%CI 0.43–0.52), and the PPV and NPV were 0.62 (95%CI 0.60–0.64) and 0.58 (95%CI 0.54–0.62).ConclusionsThe NTS decision support tool used in Dutch OHS-PC performed poor to moderately regarding safety (sensitivity) and efficiency (specificity) in allocating adequate urgencies to patients with and without TIA/stroke/other LTEs.Trial registration: the Netherlands National Trial Register, identification number NTR7331.

scholarly journals Two-Dimensional Identification of Fetal Tooth Germs

2017 ◽  
Vol 54 (2) ◽  
pp. 166-169 ◽  
Author(s):  
Mariana Seabra ◽  
Paula Vaz ◽  
Francisco Valente ◽  
Ana Braga ◽  
António Felino
Keyword(s):  
Outcome Measure ◽  
First Trimester ◽  
Cross Sectional Study ◽  
Trisomy 13 ◽  
Two Dimensional ◽  
Sectional Study ◽  
Cross Sectional ◽  
Fetal Biometry ◽  
Maxillary Tooth ◽  
Tooth Germs

Objective To demonstrate the efficiency and applicability of two-dimensional ultrasonography in the identification of tooth germs and in the assessment of potential pathology. Design Observational, descriptive, cross-sectional study. Setting Prenatal Diagnosis Unit of Centro Hospitalar de Vila Nova de Gaia / Espinho–Empresa Pública in Portugal. Patients A total of 157 white pregnant women (median age, 32 years; range, 14 to 47 years) undergoing routine ultrasound exams. Main Outcome Measure(s) Description of the fetal tooth germs, as visualized by two-dimensional ultrasonography, including results from prior fetal biometry and detailed screening for malformations. Results In the first trimester group, ultrasonography identified 10 tooth germs in the maxilla and 10 tooth germs in the mandible in all fetuses except for one who presented eight maxillary tooth germs. This case was associated with a chromosomal abnormality (trisomy 13) with a bilateral cleft palate. In the second and third trimesters group, ultrasonography identified a larger range of tooth germs: 81.2% of fetuses showed 10 tooth germs in the maxilla and 85.0% of fetuses had 10 tooth germs in the mandible. Hypodontia was more prevalent in the maxilla than in the mandible, which led us to use qualitative two-dimensional ultrasonography to analyze the possible association between hypodontia and other variables such as fetal pathology, markers, head, nuchal, face, and spine. Conclusions We recommend using this method as the first exam to evaluate fetal morphology and also to help establish accurate diagnosis of abnormalities in pregnancy.

scholarly journals Percutaneous Two-Dimensional Shear Wave Elastography for Diagnosis of Pancreatic Tumor

Diagnostics ◽  
2021 ◽  
Vol 11 (3) ◽  
pp. 498
Author(s):  
Yotaro Iino ◽  
Hitoshi Maruyama ◽  
Rintaro Mikata ◽  
Shin Yasui ◽  
Keisuke Koroki ◽  
...  
Keyword(s):  
Shear Wave ◽  
Shear Wave Elastography ◽  
Cross Sectional Study ◽  
Ductal Adenocarcinoma ◽  
Pancreatic Tumors ◽  
Two Dimensional ◽  
Cross Sectional ◽  
Tumor Lesion ◽  
Tumor Tissues ◽  
Specific Mapping

Background: To investigate the efficacy of two-dimensional shear wave elastography (2D-SWE) for the diagnosis of pancreatic mass lesions. Methods: This ethics committee–approved cross-sectional study included 52 patients with histologically-proven pancreatic tumors (pancreatic ductal adenocarcinoma (PDAC), 36; tumor-forming pancreatitis (TFP), 15; neuroendocrine tumor, 1) and 33 control subjects. The 2D-SWE was performed for the tumor/non-tumor tissues, and SWE-mapping patterns and propagation quality were assessed. Results: Three mapping patterns were detected based on the size and distribution of the coloring areas. Pattern A (whole coloring) was detected in all non-tumor tissues and TFP, whereas pattern C (multiple small coloring spots) was detected in PDAC only. Pattern B (partial coloring with smaller spots) was detected in other lesions. The specificity and positive predictive value of pattern A for non-PDAC and those of pattern C for PDAC were 100%. The SWE value was higher in tumor lesions than in the non-tumor tissues (38.1 vs. 9.8 kPa; p < 0.001) in patients with PDAC. The SWE value in the non-tumor lesion was higher in patients with PDAC than in control (9.8 vs. 7.5 kPa; p < 0.001). Conclusions: 2D-SWE may play a role as a novel diagnostic tool for PDAC to detect a specific mapping pattern with quantitative assessment.

Biomechanical properties of common carotid arteries assessed by circumferential two-dimensional strain and beta stiffness index in patients with ankylosing spondylitis

2020 ◽  
pp. jrheum.200146
Author(s):  
Helena Forsblad-d’Elia ◽  
Lucy Law ◽  
Karin Bengtsson ◽  
Johan Smeds ◽  
Maria Ketonen ◽  
...  
Keyword(s):  
Ankylosing Spondylitis ◽  
Arterial Stiffness ◽  
Biomechanical Properties ◽  
Cross Sectional Study ◽  
Stiffness Index ◽  
Two Dimensional ◽  
Related Factors ◽  
Cross Sectional ◽  
2D Strain ◽  
Age And Sex

Objective Ankylosing spondylitis (AS) is associated with an elevated risk of cardiovascular disease (CVD) related to atherosclerosis, preceded by arterial stiffness. We aimed to examine common carotid artery (CCA) biomechanical properties using ultrasound to calculate β stiffness index (indicating arterial stiffness) and, a more recently developed technique, two-dimensional (2D) speckle tracking strain (indicating arterial motion and deformation, strain) to 1) compare with age- and sex-matched controls and to 2) analyze relationships between strain and stiffness with disease characteristics and traditional risk factors for CVD in AS patients. Methods In this cross-sectional study, a cohort of 149 patients with AS, mean age 55.3±11.2 years, 102(68.5%) men, 146 (98%) HLA-B27 positive, were examined. Bilateral CCAs were examined for circumferential 2D strain and β stiffness index. A subgroup of 46 patients were compared with 46 age- and sex-matched controls, both groups without hypertensive disease, diabetes, myocardial infarction or stroke. Results Mean bilateral circumferential 2D strain was lower in AS patients compared with controls, 7.9±2.6% vs 10.3±1.9%, p<0.001 whereas mean bilateral β stiffness index was higher, 13.1±1.6mmHg/mm vs 12.3±1.3mmHg/mm, p=0.018. In multivariable linear regression analyses strain was associated with age, erythrocyte sedimentation rate, history of anterior uveitis and treatment with csDMARD and/or bDMARD (R2 0.33), while stiffness was associated with age (R2 0.19). Conclusion Both CCA circumferential 2D strain and β stiffness index differed between AS patients and controls. Strain was associated with AS-related factors and age while stiffness with age, suggesting that the obtained results reflect different pathogenic vascular processes.

Sign in / Sign up

Export Citation Format

Share Document